update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,98 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: distilbert-base-uncased-finetuned-infovqa
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
+
should probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# distilbert-base-uncased-finetuned-infovqa
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 2.8872
|
18 |
+
|
19 |
+
## Model description
|
20 |
+
|
21 |
+
More information needed
|
22 |
+
|
23 |
+
## Intended uses & limitations
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Training and evaluation data
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training procedure
|
32 |
+
|
33 |
+
### Training hyperparameters
|
34 |
+
|
35 |
+
The following hyperparameters were used during training:
|
36 |
+
- learning_rate: 0.0001
|
37 |
+
- train_batch_size: 4
|
38 |
+
- eval_batch_size: 4
|
39 |
+
- seed: 250500
|
40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
+
- lr_scheduler_type: linear
|
42 |
+
- num_epochs: 1
|
43 |
+
|
44 |
+
### Training results
|
45 |
+
|
46 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
47 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
48 |
+
| No log | 0.02 | 100 | 4.7706 |
|
49 |
+
| No log | 0.05 | 200 | 4.4399 |
|
50 |
+
| No log | 0.07 | 300 | 3.8175 |
|
51 |
+
| No log | 0.09 | 400 | 3.8306 |
|
52 |
+
| 3.3071 | 0.12 | 500 | 3.6480 |
|
53 |
+
| 3.3071 | 0.14 | 600 | 3.6451 |
|
54 |
+
| 3.3071 | 0.16 | 700 | 3.4974 |
|
55 |
+
| 3.3071 | 0.19 | 800 | 3.4686 |
|
56 |
+
| 3.3071 | 0.21 | 900 | 3.4703 |
|
57 |
+
| 3.5336 | 0.23 | 1000 | 3.3165 |
|
58 |
+
| 3.5336 | 0.25 | 1100 | 3.3634 |
|
59 |
+
| 3.5336 | 0.28 | 1200 | 3.3466 |
|
60 |
+
| 3.5336 | 0.3 | 1300 | 3.3411 |
|
61 |
+
| 3.5336 | 0.32 | 1400 | 3.2456 |
|
62 |
+
| 3.3593 | 0.35 | 1500 | 3.3257 |
|
63 |
+
| 3.3593 | 0.37 | 1600 | 3.2941 |
|
64 |
+
| 3.3593 | 0.39 | 1700 | 3.2581 |
|
65 |
+
| 3.3593 | 0.42 | 1800 | 3.1680 |
|
66 |
+
| 3.3593 | 0.44 | 1900 | 3.2077 |
|
67 |
+
| 3.2436 | 0.46 | 2000 | 3.2422 |
|
68 |
+
| 3.2436 | 0.49 | 2100 | 3.2529 |
|
69 |
+
| 3.2436 | 0.51 | 2200 | 3.2681 |
|
70 |
+
| 3.2436 | 0.53 | 2300 | 3.1055 |
|
71 |
+
| 3.2436 | 0.56 | 2400 | 3.0174 |
|
72 |
+
| 3.093 | 0.58 | 2500 | 3.0608 |
|
73 |
+
| 3.093 | 0.6 | 2600 | 3.0200 |
|
74 |
+
| 3.093 | 0.63 | 2700 | 2.9884 |
|
75 |
+
| 3.093 | 0.65 | 2800 | 3.0041 |
|
76 |
+
| 3.093 | 0.67 | 2900 | 2.9700 |
|
77 |
+
| 3.0087 | 0.69 | 3000 | 3.0993 |
|
78 |
+
| 3.0087 | 0.72 | 3100 | 3.0499 |
|
79 |
+
| 3.0087 | 0.74 | 3200 | 2.9317 |
|
80 |
+
| 3.0087 | 0.76 | 3300 | 3.0817 |
|
81 |
+
| 3.0087 | 0.79 | 3400 | 3.0035 |
|
82 |
+
| 2.9694 | 0.81 | 3500 | 3.0850 |
|
83 |
+
| 2.9694 | 0.83 | 3600 | 2.9948 |
|
84 |
+
| 2.9694 | 0.86 | 3700 | 2.9874 |
|
85 |
+
| 2.9694 | 0.88 | 3800 | 2.9202 |
|
86 |
+
| 2.9694 | 0.9 | 3900 | 2.9322 |
|
87 |
+
| 2.8277 | 0.93 | 4000 | 2.9195 |
|
88 |
+
| 2.8277 | 0.95 | 4100 | 2.8638 |
|
89 |
+
| 2.8277 | 0.97 | 4200 | 2.8809 |
|
90 |
+
| 2.8277 | 1.0 | 4300 | 2.8872 |
|
91 |
+
|
92 |
+
|
93 |
+
### Framework versions
|
94 |
+
|
95 |
+
- Transformers 4.11.3
|
96 |
+
- Pytorch 1.9.0+cu111
|
97 |
+
- Datasets 1.14.0
|
98 |
+
- Tokenizers 0.10.3
|